An Operating System Support to Low-Overhead Communications in NOW Clusters

This paper describes an Operating System approach to the problem of delivering low latency high bandwidth communications for PC clusters running a public domain OS like Linux and connected by standard, off-the-shelf networks like Fast-Ethernet. The PARMA 2 project has the main goal of designing the new light-weight protocol suite PRP, in order to drastically reduce the software overhead introduced by TCP/IP. PRP wants to offer at high level a stream socket oriented interface and at low level compatibility with any device driver. High level compatibility is crucial in facilitating the porting on PRP of existing applications or message passing packages. Moreover, an optimized version of MPI, based on PRP and evolution of the widespread MPICH implementation, is under development, allowing for a very effective reduction of the communication latencies in synchronous communications, compared to the TCP/IP-based MPI. 1